{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:43:26Z","timestamp":1772865806512,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62066033"],"award-info":[{"award-number":["62066033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61773224"],"award-info":[{"award-number":["61773224"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017186","name":"Ohio Supercomputer Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017186","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006928","name":"Ohio State University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006928","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3107617","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T21:34:49Z","timestamp":1630359289000},"page":"2878-2887","source":"Crossref","is-referenced-by-count":9,"title":["Recurrent Neural Networks and Acoustic Features for Frame-Level Signal-to-Noise Ratio Estimation"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5963-4505","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8195-6319","authenticated-orcid":false,"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0406-1105","authenticated-orcid":false,"given":"Xueliang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2221459"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/1.3699200"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.1994.576920"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2615240"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1109\/TASL.2010.2045799","article-title":"A data-driven approach to a priori SNR estimation","volume":"19","author":"suhadi","year":"2010","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.08.003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-224"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref11","article-title":"DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM","author":"garofolo","year":"0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2295918"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref15","article-title":"Estimation of noise spectrum and its application to SNR-estimation and speech enhancement","author":"hirsch","year":"1993","journal-title":"Int Comput Sci Inst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-581"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-644"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2545928"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.3184603"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3016487"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(89)90027-2"},{"key":"ref27","article-title":"NIST speech signal to noise ratio measurements","year":"1994"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.4986931"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2687829"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-230"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.06.009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93764-9_33"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2359159"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-211"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.279283"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462275"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Int Conf Learning Representations"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00004-7"},{"key":"ref22","first-page":"4626","article-title":"Frame-level signal-to-noise ratio estimation using deep learning","author":"li","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref21","first-page":"123","article-title":"Robust estimation of the SNR of noisy speech signals for the quality evaluation of speech databases","author":"korthauer","year":"1999","journal-title":"Workshop on Robust Methods for Speech Recognition in Adverse Conditions"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854294"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952152"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-319-22482-4_11","article-title":"Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR","author":"weninger","year":"2015","journal-title":"Proc Int Conf Latent Variable Anal Signal Separation"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-225"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/97.769361"},{"key":"ref43","first-page":"1589","article-title":"Robust speaker identification using auditory features and computational auditory scene analysis","author":"shao","year":"2008","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205242"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09525289.pdf?arnumber=9525289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:54Z","timestamp":1652194434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9525289\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3107617","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}